用对抗网络重构聚类损失，让深度聚类更稳定高效。
Deep clustering using adversarial net based clustering loss
- 将传统KL散度聚类损失改造为对抗训练框架
- 在MNIST、REUTERS10K等数据集上达到顶尖性能
- 适合追求高稳定性聚类效果的研究者
深度聚类是结合深度学习与传统无监督聚类的新方法，其核心在于设计一个损失函数，使样本在隐空间中远离其真实聚类中心。概率型深度聚类使用KL散度重构损失函数。但主流方法受限于需闭式表达以支持反向传播。受深度聚类与对抗网络启发，本文将深度聚类重新建模为基于传统闭式KL散度的对抗网络。训练过程变为最小化编码器损失、最大化判别器损失。理论上，最优解时该方法逼近编码器与判别器分布间的JS散度。我们在多个经典数据集（如MNIST、REUTERS10K、CIFAR10）上验证了方法性能，结果与部分当前最优深度聚类方法相当或更优。
原文摘要 · Abstract (English)
Deep clustering is a recent deep learning technique which combines deep learning with traditional unsupervised clustering. At the heart of deep clustering is a loss function which penalizes samples for being an outlier from their ground truth cluster centers in the latent space. The probabilistic variant of deep clustering reformulates the loss using KL divergence. Often, the main constraint of deep clustering is the necessity of a closed form loss function to make backpropagation tractable. Inspired by deep clustering and adversarial net, we reformulate deep clustering as an adversarial net over traditional closed form KL divergence. Training deep clustering becomes a task of minimizing the encoder and maximizing the discriminator. At optimality, this method theoretically approaches the JS divergence between the distribution assumption of the encoder and the discriminator. We demonstrated the performance of our proposed method on several well cited datasets such as MNIST, REUTERS10K and CIFAR10, achieving on-par or better performance with some of the state-of-the-art deep clustering methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。